Veynandt, Francois
Official Name
Veynandt, Francois
Main Affiliation
Jobtitel
Key Researcher
Email
francois.veynandt@hochschule-burgenland.at
ORCID
Scopus Author ID
55700195500
OpenAlex ID
A5000108343
18 results
Now showing 1 - 10 of 18
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, DEEP NEURAL NETWORKS FOR OBJECT-DETECTION AND INSTANCE SEGMENTATION OF MECHANICAL, ELECTRICAL AND PLUMBING COMPONENTS: TRANSFER LEARNING ON RADIATORS AS AN EXAMPLE(European Council for Computing in Construction, 2025-01-01); ; ; ; Partl R.Cost estimation and as-built documentation on construction sites require extensive manual work. Combining LiDAR with computer vision offers an effective solution for 5D BIM applications. Therefore, two deep neural networks are trained on a database of over 1000 images of radiators, as example of MEP components. Transfer learning has been applied on SOLOv2 for instance segmentation and on YOLOx for object detection. Given the variety of the image database, the generated models achieve satisfying performance, suitable for the intended applications. The developed models will be used in a scan-to-BIM workflow, enabling the semi-automatic capture of as-built information.3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Real long-term performance evaluation of an improved office building operation involving a Data-driven model predictive control(Elsevier BV, 2025-03); ; ; ; Zogas, PanagiotisScopus© Citations 10 51 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Measurement data from real operation of a hybrid photovoltaic-thermal solar collectors, used for the development of a data-driven model(2023); ; ; This article presents a measurement dataset from real operation of a hybrid photovoltaic-thermal solar collector. The data is from a summer period, when the collector works at its higher temperature limit, with low thermal efficiency. The dataset characterizes the output of the collector: thermal (heat transfer fluid flowrate, inlet and outlet temperatures) and electrical (raw current and voltage, Hampel filtered power). Further information on the collector are the PV cell temperature and the back surface temperature (in three points). It provides detailed weather information: ambient temperature, solar resource (direct normal, global and diffuse horizontal, global tilted in the collector plane), equivalent radiative sky temperature (calculated from a pyrgeometer), wind speed and direction both horizontal and in the tilted collector plane. The calculated sun position with Duffie and Beckmann method is also given (elevation and azimuth) . The dataset covers 58 summer days from 11th July to 6th September, with a 5 second time step. The data is available as .mat file (MATLAB) and .csv file. A selection of variables from this dataset has already been used in the development of a data-driven model (see related article) [1]. The extended data presented in this article offers mode detailed weather information, opening further investigations opportunities. Further options for data-driven modelling of PVT collectors could be investigated. The correlation of wind related losses to horizontal wind measurements could be compared to a model with wind measurements in the collector plane. The dataset could support the validation of solar models, with direct and diffuse shares on the horizontal or in the tilted plane. [Duck Duck Go](https://duckduckgo.com)Scopus© Citations 6 84 29 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Monitoring data from an office room in a real operating building, suitable for state-space energy modelling(2024); ; ; The dataset provides all necessary variables for data-driven energy modelling of an office room. The measurement data have been obtained from an office building operating as living lab in a temperate climate of Central Europe. The temperatures and the ventilation air flowrate are raw measurements, while the heat flows are calculated from measurements. The incoming solar irradiance is calculated with two façade models –simple and enhanced–, using measurements (solar irradiance, movable shading settings) and building characteristics (geometry, glazing and shading properties). One year and four months of data is provided with a fine one-minute time step and a coarser fifteen-minute time step. The dataset can be used to test and validate data-driven models, for example for predictive control applications.Scopus© Citations 6 43 30 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Scopus© Citations 3 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Economic comparison of reference solar thermal systems for households in five European countries(Elsevier, 2019); 1Scopus© Citations 20 98 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Cacao and coffee roasting using concentrated solar energy: A technology for small farmers in rural areas of Peru(River Publishers, 2016); 1 64 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Scopus© Citations 7 7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Modeling of solar radiation transmission through triple glazing based only on on-site measurements(2020); A model is developed which can calculate the irradiance behind a glazed façade, based on measured incident solar radiation. Data from a real office building is used to establish and test the model. Onsite irradiance measurements on both sides of the facades are exploited to calibrate the model. The main parameters are the average diffuse transmittance and a correlation for the direct transmittance, as a function of the incidence angle. Correction of the measurements, including the frame reflection, are taken into account. Hence, the model contributes to the solar heat flux identification, in the perspective of model predictive control application.39 15 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, 2Scopus© Citations 39 28